arXiv:2607. 19949v1 Announce Type: new Abstract: Smartphone personal assistants reason over longitudinal personal data, yet evaluating them requires context-rich evaluation data whose correct answers are known, and real device traces are too privacy-sensitive to share.
arXiv:2609.25373v1 Announce Type: new Abstract: On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or na...
arXiv:2608. 10692v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions.
CallScreenBench is a benchmark for evaluating small, on-device language models that act as phone secretaries, focusing on their ability to handle unknown inbound calls without a cooperative task. The benchmark measures owner endorsement through five call-and-note metrics, each paired with counter-metrics and uncertainty estimates, and includes guardedness diagnostics to identify safe, tool‑free proxies. Results across 4‑bit checkpoints of 0.6‑4 B parameter models show varying performance on service, recall, plausibility, and triage discrimination, highlighting trade‑offs between quality and guardedness.
arXiv:2605. 29486v2 Announce Type: replace-cross Abstract: A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale.
The paper introduces a three-tier persona vector for user simulation in evaluating LLM agents, comprising 23 dimensions across demographics, behavioral traits, and emotional states, plus a query-complexity overlay. It demonstrates that these nuanced personas generate diverse, scenario-reactive conversations, leading to significant variations in agent goal achievement and compliance across different contexts. The model’s design allows for reproducible, auditable user behavior patterns without relying on learned covariance matrices.
arXiv:2606.26403v2 Announce Type: replace Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and...
MTVA-Bench is a new benchmark designed to evaluate the language model component of cascaded voice agents under realistic conditions. It simulates callers with an LLM, mocks backend tool responses, and scores both tool‑call correctness and conversational quality using two LLM judges, covering 49 agents, 490 scenarios, and 7 languages. The benchmark reveals that while models perform similarly on tool selection, they differ widely in argument handling, rule compliance, and dialogue quality, highlighting the nuanced challenges of real‑world voice interactions.
ContextEcho is a benchmark and harness designed to measure persona drift in large language models during long, tool‑using coding sessions. It includes a 25‑probe identity suite, a snapshot‑then‑probe protocol that preserves the main conversation, and both judged and judge‑free measurement surfaces. Across 23 frontier models and thousands of turns, the benchmark shows that persona drift is widespread, not limited to specific model families, and that simple in‑session compaction does not reset it, while a single‑shot anchor can restore the intended persona.
arXiv:2606. 09764v1 Announce Type: new Abstract: A useful phone agent needs to be personally intelligent.
The paper introduces a three-tier persona vector to generate diverse, realistic user inputs for evaluating tool-augmented LLM agents. The vector includes 23 dimensions: categorical demographics, continuous behavioral traits, and continuous emotional states, plus a query-complexity overlay. Experiments on 64,698 conversations show that these persona dimensions produce measurable differences in agent performance and realistic scenario-reactive behavior.
MobileGym is a browser-hosted, lightweight simulation platform designed for mobile GUI agent research. It offers verifiable outcome signals via deterministic, JSON-based state judging and supports scalable online reinforcement learning with hundreds of parallel instances on a single server. The platform includes a declarative task-definition framework, a structured AnswerSheet protocol, and a benchmark of 416 parameterized tasks across 28 apps, demonstrating strong sim-to-real transfer in a case study.
arXiv:2608. 02613v1 Announce Type: cross Abstract: Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models.